Outer Step 0. Inner Step 160. Batch Size 428

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156193,
-    5156200,
-    5156205,
-    5156211,
-    5156215,
-    5156221,
-    5156226,
-    5156231,
-    5156235,
-    5156239
+    5156270,
+    5156274,
+    5156279,
+    5156283,
+    5156289,
+    5156293,
+    5156299,
+    5156304,
+    5156309,
+    5156315
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 152,
+  "inner_step": 160,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2a3be46d2e2c5ab47226e57b22257807d81a27dfd324be232273095c4624f4
+oid sha256:0a0790e146a1a936974de8c366d4a2eaa1db22d2aafe9be2ec4287f12362cbab
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec8b86ab3e7a7eedfeed54ddb2572214d4361945505ca85d822c40db588d91d
+oid sha256:e80c63a5fa2d624c41422a4ef85fb910b94783473340ec0cbff41b1e0206a6d7
 size 4040701744